© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10429
    Prev
    Next
    INDEX
    Explanations

    Java package declarations and keywords associated with Java source code

    oai_token-act-pair · gemini-2.0-flash

    package

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    package
    -1.38
     package
    -1.05
    Package
    -1.05
     Package
    -1.04
     PACKAGE
    -0.97
     packages
    -0.91
    PACKAGE
    -0.87
     Packages
    -0.77
    Packages
    -0.75
    Pkg
    -0.74
    POSITIVE LOGITS
    <bos>
    0.54
    WriteLiteral
    0.53
    /******/
    0.49
    Rüyada
    0.48
    liothèque
    0.47
     jScrollPane
    0.46
     للتو
    0.44
    ftn
    0.44
    WTS
    0.43
    ɵ
    0.43
    Activations Density 2.009%

    No Known Activations